Download Latest Version lemonade-embeddable-11.8.1-windows-x64.zip (5.3 MB)
Email in envelope

Get an email when there's a new version of Lemonade

Home / v11.6.0
Name Modified Size InfoDownloads / Week
Parent folder
Lemonade-11.6.0-Darwin.pkg 2026-08-14 14.1 MB
0
lemonade-embeddable-11.6.0-macos-arm64.tar.gz 2026-08-14 5.4 MB
0
lemonade-embeddable-11.6.0-ubuntu-arm64.tar.gz 2026-08-14 6.5 MB
0
lemonade-embeddable-11.6.0-ubuntu-x64.tar.gz 2026-08-14 7.0 MB
0
lemonade-embeddable-11.6.0-windows-x64.zip 2026-08-14 5.1 MB
0
lemonade-server-11.6.0-fc43.aarch64.rpm 2026-08-14 6.1 MB
0
lemonade-server-11.6.0-fc43.x86_64.rpm 2026-08-14 6.7 MB
0
lemonade-server-11.6.0-fc44.aarch64.rpm 2026-08-14 6.0 MB
0
lemonade-server-11.6.0-fc44.x86_64.rpm 2026-08-14 6.8 MB
0
lemonade-server-minimal.msi 2026-08-14 6.9 MB
0
lemonade-server_11.6.0-debian13_amd64.deb 2026-08-14 3.6 MB
0
lemonade-server_11.6.0-debian13_arm64.deb 2026-08-14 3.1 MB
0
lemonade.msi 2026-08-14 10.6 MB
0
README.md 2026-08-13 11.0 kB
0
v11.6.0 source code.tar.gz 2026-08-13 3.5 MB
0
v11.6.0 source code.zip 2026-08-13 3.9 MB
0
Totals: 16 Items   95.4 MB 0

Headline

  • The Muse-Glimmer-30B-GGUF model joins the built-in llama.cpp catalog with draft decoding, vision, and tool-calling support.
  • The llama.cpp ROCm backend now runs on AMD Instinct MI100, MI200, MI210, and MI250 GPUs on Linux.
  • A new experimental TheNoise ROCm image-generation backend brings Anima and Krea-2 to AMD Strix Halo and Strix Point iGPUs.
  • The new lemonade alias commands let you assign your own names to models, with alias-aware /v1/models listing and admin endpoints.
  • lemonade bench adds opt-in vision benchmark scenarios for multimodal models.

Breaking Changes

  • /v1/audio/speech with stream_format=audio and a non-PCM response_format (such as mp3) against Kokoro now returns HTTP 400 (only pcm is supported) instead of silently returning PCM audio.
  • /v1/models now lists each GGUF quant in a split extra_models_dir subfolder as its own entry rather than one entry per folder; the old folder name still resolves as a hidden request alias.
  • The Windows MSI layout changed: Lemonade_Server_MSI now contains only lemonade-server-minimal.msi, and the desktop lemonade.msi now ships in a new Lemonade_Desktop_MSI artifact, so automation that reads lemonade.msi from the old artifact must be repointed.

Lemonade Server

Operating System Downloads
Windows lemonade.msi (github.com)
Ubuntu 24.04+ Launchpad PPA
Debian 13 (x86_64) lemonade-server_11.6.0-debian13_amd64.deb (github.com)
Debian 13 (ARM64) lemonade-server_11.6.0-debian13_arm64.deb (github.com)
Fedora 43 (x86_64) lemonade-server-11.6.0-fc43.x86_64.rpm (github.com)
Fedora 43 (ARM64) lemonade-server-11.6.0-fc43.aarch64.rpm (github.com)
Fedora 44 (x86_64) lemonade-server-11.6.0-fc44.x86_64.rpm (github.com)
Fedora 44 (ARM64) lemonade-server-11.6.0-fc44.aarch64.rpm (github.com)
macOS Lemonade-11.6.0-Darwin.pkg (github.com)

Other platforms? See our Installation Options for Docker, Snap, Arch, Debian, and more.

Embeddable Lemonade

Portable binaries for bundling into your own installer. Run lemond ./ as a subprocess.

Platform Download
Ubuntu x64 lemonade-embeddable-11.6.0-ubuntu-x64.tar.gz (github.com)
Ubuntu arm64 lemonade-embeddable-11.6.0-ubuntu-arm64.tar.gz (github.com)
Windows x64 lemonade-embeddable-11.6.0-windows-x64.zip (github.com)
macOS arm64 lemonade-embeddable-11.6.0-macos-arm64.tar.gz (github.com)

What's Changed

Thanks @Bekhouche, @SlawomirNowaczyk, @Yigtwxx, @ZMXJJ, @abn, @anditherobot, @bitgamma, @blackdeathdrow, @ckuethe, @duggiefresh, @fl0rianr, @github-actions, @hogeheer499-commits, @jeremyfowers, @kenvandine, @popey, @ramkrishna2910, @sreeram-11, @storm1er, @superm1 for your awesome contributions to this release!

Click to expand changelog * fix(ci): prevent MSI verify flake from stale ARP entries on shared runners by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2895 * docs: add testing guide by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2891 * fix(build): patch libwebsockets GENHDR OUTPUT to silence MSB8065 by @blackdeathdrow in https://github.com/lemonade-sdk/lemonade/pull/2893 * ci: stop re-running the full suite on push to main by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2899 * fix(cli): respect explicit --port when --host includes a scheme by @kenvandine in https://github.com/lemonade-sdk/lemonade/pull/2914 * README.md - Fix download links by @duggiefresh in https://github.com/lemonade-sdk/lemonade/pull/2827 * ci: run packaging, PPA, distro, macOS and backend-validation jobs in the merge queue by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2911 * New helper combining add_test() and register_cpp_ci_test() by @SlawomirNowaczyk in https://github.com/lemonade-sdk/lemonade/pull/2877 * [llamacpp] replace deprecated flags, better IO flag handling by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/2833 * Add /rerank as the reranking endpoint path (alias /reranking) by @sreeram-11 in https://github.com/lemonade-sdk/lemonade/pull/2924 * fix(server): keep interrupted variantless model downloads resumable by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/2876 * test: cover embeddings missing model error by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/2061 * fix(docs): Added group_add configuration for ROCm support in Docker. by @storm1er in https://github.com/lemonade-sdk/lemonade/pull/2857 * ci: run .exe/.deb inference suites in the merge queue by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2950 * ci: isolate llama.cpp validation cleanup on self-hosted runners by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/2915 * Reclaim routing helpers when a router collection's policy changes by @SlawomirNowaczyk in https://github.com/lemonade-sdk/lemonade/pull/2795 * [backends] Add support for image generation through TheNoise by @bitgamma in https://github.com/lemonade-sdk/lemonade/pull/2927 * fix(ci): refactor cleanup and improve logging llama.cpp validation by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/2992 * fix(server): frame backend errors as SSE events on the streaming path by @Yigtwxx in https://github.com/lemonade-sdk/lemonade/pull/2975 * ci: cut the longest test jobs via parameter tuning by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2953 * docs: add new engine logos to homepage engine ticker by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2920 * Show all local model versions in one folder by @anditherobot in https://github.com/lemonade-sdk/lemonade/pull/2107 * test: run the committed model-type classifier test in CI by @Yigtwxx in https://github.com/lemonade-sdk/lemonade/pull/2976 * fix(server): return the router error status on rerank, slots and tokenize by @Yigtwxx in https://github.com/lemonade-sdk/lemonade/pull/2974 * ci(test): speed up server job suite by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3007 * Add complete vision benchmark support by @ckuethe in https://github.com/lemonade-sdk/lemonade/pull/2869 * ci: cut installer build time on the PR/merge-queue critical path by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/2989 * fix(server): report backend errors on the Anthropic messages bridge by @Yigtwxx in https://github.com/lemonade-sdk/lemonade/pull/3006 * docs: add Muse Glimmer 30B blog post by @jeremyfowers in https://github.com/lemonade-sdk/lemonade/pull/3033 * fix: add GITHUB_TOKEN / GH_TOKEN support to GitHub API requests by @blackdeathdrow in https://github.com/lemonade-sdk/lemonade/pull/2995 * ci: fail fast in merge queue matrices by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3014 * feat(rocm): enable AMD Instinct MI100 (gfx908) and MI200 (gfx90a) in llama.cpp ROCm by @kenvandine in https://github.com/lemonade-sdk/lemonade/pull/2092 * feat(router): report estimated cost on collection.router decisions by @Bekhouche in https://github.com/lemonade-sdk/lemonade/pull/2763 * Allow explicit system llama.cpp backend by @popey in https://github.com/lemonade-sdk/lemonade/pull/3016 * feat(server): add model alias system with /v1/models listing and /internal/aliases endpoints by @abn in https://github.com/lemonade-sdk/lemonade/pull/2818 * fix(server): sum sibling shards when computing on-disk GGUF size by @blackdeathdrow in https://github.com/lemonade-sdk/lemonade/pull/2973 * fix(tts): stop dropping response_format on the streaming path by @ZMXJJ in https://github.com/lemonade-sdk/lemonade/pull/3029 * fix: honor custom backend binary environment variables by @hogeheer499-commits in https://github.com/lemonade-sdk/lemonade/pull/3004 * Update llama.cpp to b10360 by @github-actions[bot] in https://github.com/lemonade-sdk/lemonade/pull/3053 * Add support for a default model source by @superm1 in https://github.com/lemonade-sdk/lemonade/pull/3036 * feat(llamacpp): auto-detect draft GGUF companions by @fl0rianr in https://github.com/lemonade-sdk/lemonade/pull/3051 * Bump project version from 11.5.2 to 11.6.0 by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/3085 * feat(models): add Muse Glimmer 30B to the model catalog by @ramkrishna2910 in https://github.com/lemonade-sdk/lemonade/pull/3090 * Update llama.cpp to b10375 by @github-actions[bot] in https://github.com/lemonade-sdk/lemonade/pull/3097

New Contributors

Full Changelog: https://github.com/lemonade-sdk/lemonade/compare/v11.5.2...v11.6.0

Windows installers are signed. Free code signing provided by SignPath.io, certificate by SignPath Foundation. See our Code Signing Policy.

Source: README.md, updated 2026-08-13